Compare commits

..
Author SHA1 Message Date
Sharang ParnerkarandClaude Fable 5 54cf39383c feat(oscal): emit unmapped findings as-is + MCP oscal_assessment tool
CI / Check (push) Skipped
CI / Check (pull_request) Successful in 5m50s
CI / Detect Changes (pull_request) Skipped
CI / Deploy Agent (pull_request) Skipped
CI / Deploy Dashboard (pull_request) Skipped
CI / Deploy Docs (pull_request) Skipped
CI / Deploy MCP (pull_request) Skipped
The OSCAL emitter now reports EVERY non-false-positive finding: mapped findings
(via their stamped control_refs) target their controls; UNMAPPED findings are
emitted as standalone observations, reported as-is (cwe/tool/severity props) so
nothing is lost — they can be mapped later as the LUT / master-controls grow.
assess() keys off Finding.control_refs now, not the CWE linker.

New compliance-mcp `oscal_assessment` tool serves this OSCAL over MCP — what
breakpilot's scanner_mcp_client pulls. Assess endpoint simplified to match.
Emitter tests cover mapped / unmapped-as-is / false-positive-excluded.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 11:33:09 +02:00
16 changed files with 93 additions and 1224 deletions
+8 -16
View File
@@ -206,13 +206,11 @@ jobs:
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=repo.meghsakha.com/certifai/compliance-agent
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login repo.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
IMAGE=registry.meghsakha.com/compliance-agent
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.agent -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
command -v cosign >/dev/null 2>&1 || { curl -sSfLo /usr/local/bin/cosign https://github.com/sigstore/cosign/releases/download/v2.4.3/cosign-linux-amd64 && chmod +x /usr/local/bin/cosign; }
cosign sign --yes --key env://COSIGN_KEY "$IMAGE:latest" || echo "::warning::cosign failed"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy agent"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"
@@ -232,13 +230,11 @@ jobs:
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=repo.meghsakha.com/certifai/compliance-dashboard
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login repo.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
IMAGE=registry.meghsakha.com/compliance-dashboard
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.dashboard -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
command -v cosign >/dev/null 2>&1 || { curl -sSfLo /usr/local/bin/cosign https://github.com/sigstore/cosign/releases/download/v2.4.3/cosign-linux-amd64 && chmod +x /usr/local/bin/cosign; }
cosign sign --yes --key env://COSIGN_KEY "$IMAGE:latest" || echo "::warning::cosign failed"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy dashboard"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"
@@ -256,12 +252,10 @@ jobs:
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=repo.meghsakha.com/certifai/compliance-docs
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login repo.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
IMAGE=registry.meghsakha.com/compliance-docs
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
docker build -f Dockerfile.docs -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
command -v cosign >/dev/null 2>&1 || { curl -sSfLo /usr/local/bin/cosign https://github.com/sigstore/cosign/releases/download/v2.4.3/cosign-linux-amd64 && chmod +x /usr/local/bin/cosign; }
cosign sign --yes --key env://COSIGN_KEY "$IMAGE:latest" || echo "::warning::cosign failed"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy docs"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"
@@ -281,13 +275,11 @@ jobs:
apk add --no-cache git curl openssl
git init && git remote add origin "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}.git"
git fetch --depth=1 origin "${GITHUB_SHA}" && git checkout FETCH_HEAD
IMAGE=repo.meghsakha.com/certifai/compliance-mcp
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login repo.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
IMAGE=registry.meghsakha.com/compliance-mcp
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login registry.meghsakha.com -u "${{ secrets.REGISTRY_USERNAME }}" --password-stdin
DOCKER_BUILDKIT=1 docker build --secret id=tramiton_token,env=TRAMITON_FETCH_TOKEN \
-f Dockerfile.mcp -t "$IMAGE:latest" -t "$IMAGE:${GITHUB_SHA}" .
docker push "$IMAGE:latest" && docker push "$IMAGE:${GITHUB_SHA}"
command -v cosign >/dev/null 2>&1 || { curl -sSfLo /usr/local/bin/cosign https://github.com/sigstore/cosign/releases/download/v2.4.3/cosign-linux-amd64 && chmod +x /usr/local/bin/cosign; }
cosign sign --yes --key env://COSIGN_KEY "$IMAGE:latest" || echo "::warning::cosign failed"
PAYLOAD=$(printf '{"ref":"refs/heads/main","repository":{"full_name":"sharang/compliance-scanner-agent"},"head_commit":{"id":"%s","message":"deploy mcp"}}' "${GITHUB_SHA}")
SIG=$(printf '%s' "$PAYLOAD" | openssl dgst -sha256 -hmac "${{ secrets.ORCA_WEBHOOK_SECRET }}" | awk '{print $2}')
RESP=$(curl -fsS -w "\nHTTP %{http_code}" -X POST "http://46.225.100.82:6880/api/v1/webhooks/github" -H "Content-Type: application/json" -H "X-Hub-Signature-256: sha256=$SIG" -d "$PAYLOAD"); echo "$RESP"
-117
View File
@@ -1,117 +0,0 @@
# Custom semgrep rules for CRA controls that no off-the-shelf ruleset digs out.
# Each rule id is `cra-ai-<n>-<slug>` and is keyed back to its control via the
# `control-map` LUT (by rule-id suffix, so semgrep's path prefix on check_id does
# not matter). Detection here is deterministic; the grounded LLM judge downstream
# only confirms/refutes — it never detects. Keep patterns tight: a false positive
# that the judge refutes marks the whole finding a false positive.
rules:
# --- cra-ai-1: Secure-by-Default-Konfiguration -------------------------------
- id: cra-ai-1-flask-debug-enabled
languages: [python]
severity: WARNING
message: Flask app started with debug=True — ships an interactive debugger / code execution in production (secure-by-default violation).
metadata:
cwe: ["CWE-489: Active Debug Code"]
control: cra-ai-1
patterns:
- pattern: '$APP.run(..., debug=True, ...)'
- id: cra-ai-1-django-debug-true
languages: [python]
severity: WARNING
message: Django DEBUG = True — leaks stack traces / settings in production (secure-by-default violation).
metadata:
cwe: ["CWE-489: Active Debug Code"]
control: cra-ai-1
patterns:
- pattern: 'DEBUG = True'
- id: cra-ai-1-tls-verify-disabled
languages: [python]
severity: ERROR
message: TLS certificate verification disabled (verify=False) — defeats transport security by default.
metadata:
cwe: ["CWE-295: Improper Certificate Validation"]
control: cra-ai-1
patterns:
- pattern: 'requests.$M(..., verify=False, ...)'
- id: cra-ai-1-cors-wildcard
languages: [javascript, typescript]
severity: WARNING
message: CORS Access-Control-Allow-Origin set to "*" — opens the API to any origin by default.
metadata:
cwe: ["CWE-942: Permissive Cross-domain Policy with Untrusted Domains"]
control: cra-ai-1
patterns:
- pattern-either:
- pattern: '$RES.header("Access-Control-Allow-Origin", "*")'
- pattern: '$RES.setHeader("Access-Control-Allow-Origin", "*")'
# --- cra-ai-7: Starke Authentifizierung (weak password hashing) --------------
- id: cra-ai-7-weak-password-hash
languages: [python]
severity: ERROR
message: Password/secret hashed with a fast, broken digest (md5/sha1) — use a password KDF (bcrypt/scrypt/argon2).
metadata:
cwe: ["CWE-916: Use of Password Hash With Insufficient Computational Effort"]
control: cra-ai-7
patterns:
- pattern-either:
- pattern: 'hashlib.md5($PW)'
- pattern: 'hashlib.sha1($PW)'
- metavariable-regex:
metavariable: $PW
regex: '(?i).*(pass|pwd|secret|cred|token).*'
# --- cra-ai-10: Sitzungsmanagement (insecure session cookies) ----------------
- id: cra-ai-10-session-cookie-insecure
languages: [python]
severity: ERROR
message: Session cookie hardened flag explicitly disabled (Secure/HttpOnly = False) — session token exposed to theft.
metadata:
cwe: ["CWE-614: Sensitive Cookie in HTTPS Session Without 'Secure' Attribute"]
control: cra-ai-10
patterns:
- pattern-either:
- pattern: 'SESSION_COOKIE_SECURE = False'
- pattern: 'SESSION_COOKIE_HTTPONLY = False'
- id: cra-ai-10-express-cookie-insecure
languages: [javascript, typescript]
severity: ERROR
message: Express cookie set with secure/httpOnly = false — session token exposed to interception / XSS theft.
metadata:
cwe: ["CWE-614: Sensitive Cookie in HTTPS Session Without 'Secure' Attribute"]
control: cra-ai-10
patterns:
- pattern-either:
- pattern: '$RES.cookie($NAME, $VAL, {..., secure: false, ...})'
- pattern: '$RES.cookie($NAME, $VAL, {..., httpOnly: false, ...})'
# --- cra-ai-14: Speicher-Schutz / Data at Rest (weak cipher) -----------------
- id: cra-ai-14-python-weak-cipher
languages: [python]
severity: ERROR
message: Data-at-rest encrypted with a broken cipher/mode (ECB, DES, 3DES) — provides no real confidentiality.
metadata:
cwe: ["CWE-327: Use of a Broken or Risky Cryptographic Algorithm"]
control: cra-ai-14
patterns:
- pattern-either:
- pattern: 'AES.new($K, AES.MODE_ECB, ...)'
- pattern: 'DES.new(...)'
- pattern: 'DES3.new(...)'
- id: cra-ai-14-node-weak-cipher
languages: [javascript, typescript]
severity: ERROR
message: Data-at-rest encrypted with a broken cipher (DES / deprecated createCipher) — provides no real confidentiality.
metadata:
cwe: ["CWE-327: Use of a Broken or Risky Cryptographic Algorithm"]
control: cra-ai-14
patterns:
- pattern-either:
- pattern: 'crypto.createCipheriv("des-ecb", ...)'
- pattern: 'crypto.createCipheriv("des", ...)'
- pattern: 'crypto.createCipher(...)'
-6
View File
@@ -100,11 +100,5 @@ fn load_breakpilot_config() -> BreakpilotConfig {
base_url: env_var_opt("BREAKPILOT_BASE_URL"),
token: env_secret_opt("BREAKPILOT_TOKEN"),
snapshot_dir: env_var_opt("BREAKPILOT_SNAPSHOT_DIR").unwrap_or(d.snapshot_dir),
semantic_mapping: env_var_opt("BREAKPILOT_SEMANTIC_MAPPING")
.map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
.unwrap_or(d.semantic_mapping),
grounded_control_checks: env_var_opt("BREAKPILOT_GROUNDED_CHECKS")
.map(|v| v == "1" || v.eq_ignore_ascii_case("true"))
.unwrap_or(d.grounded_control_checks),
}
}
-245
View File
@@ -1,245 +0,0 @@
//! In-memory embedding index over the control corpus, for region → control
//! retrieval.
//!
//! At master-control scale (~13.6k) findings can't be mapped by CWE (the master
//! controls carry none), so we map by *similarity*: embed each control's
//! requirement text once, then for a code region pull the top-K nearest controls
//! to hand to the grounded judge. This is the retrieval half of the semantic path.
use std::path::Path;
use serde::{Deserialize, Serialize};
use sha2::{Digest, Sha256};
use compliance_core::control_check::ControlCheckSpec;
use compliance_core::error::CoreError;
use crate::llm::LlmClient;
/// A control spec paired with its requirement-text embedding.
pub struct ControlIndex {
entries: Vec<(ControlCheckSpec, Vec<f64>)>,
}
/// On-disk form of the index: the corpus identity hash plus every spec+embedding.
/// The hash lets a later scan reuse the embeddings only if the corpus is unchanged.
#[derive(Serialize, Deserialize)]
struct PersistedIndex {
corpus_hash: String,
entries: Vec<PersistedEntry>,
}
#[derive(Serialize, Deserialize)]
struct PersistedEntry {
spec: ControlCheckSpec,
embedding: Vec<f64>,
}
/// Stable hash of the corpus identity (each control's id + requirement text, in
/// order). Same catalog → same hash → the cached embeddings are reused instead of
/// re-embedding the whole corpus.
fn corpus_hash(specs: &[ControlCheckSpec]) -> String {
let mut hasher = Sha256::new();
for s in specs {
hasher.update(s.control_id.as_bytes());
hasher.update([0u8]);
hasher.update(s.requirement.as_bytes());
hasher.update([0u8]);
}
format!("{:x}", hasher.finalize())
}
impl ControlIndex {
/// Build directly from precomputed embeddings (used by tests + callers that
/// already embedded the corpus).
pub fn from_embeddings(entries: Vec<(ControlCheckSpec, Vec<f64>)>) -> Self {
Self { entries }
}
/// Load the index from `cache_path` if it still matches the current corpus,
/// otherwise embed the corpus and persist it there. This turns the per-scan
/// re-embed of the whole (~13.6k) master-control corpus into a one-time cost
/// that survives across scans; the cache self-invalidates when the catalog
/// changes (its [`corpus_hash`] no longer matches).
pub async fn load_or_build(
llm: &LlmClient,
specs: Vec<ControlCheckSpec>,
cache_path: &Path,
) -> Result<Self, CoreError> {
let hash = corpus_hash(&specs);
if let Some(index) = Self::load_cache(cache_path, &hash).await {
tracing::debug!(
controls = index.len(),
"reusing cached control embedding index"
);
return Ok(index);
}
let index = Self::build(llm, specs).await?;
if let Err(e) = index.write_cache(cache_path, &hash).await {
tracing::warn!(error = %e, "failed to persist control embedding index");
}
Ok(index)
}
/// Read a persisted index, returning it only if its corpus hash matches.
async fn load_cache(path: &Path, hash: &str) -> Option<Self> {
let raw = tokio::fs::read(path).await.ok()?;
let persisted: PersistedIndex = serde_json::from_slice(&raw).ok()?;
if persisted.corpus_hash != hash {
return None;
}
Some(Self {
entries: persisted
.entries
.into_iter()
.map(|e| (e.spec, e.embedding))
.collect(),
})
}
/// Persist the index atomically (temp file + rename) keyed by corpus hash.
async fn write_cache(&self, path: &Path, hash: &str) -> Result<(), CoreError> {
if let Some(parent) = path.parent() {
tokio::fs::create_dir_all(parent).await?;
}
let persisted = PersistedIndex {
corpus_hash: hash.to_string(),
entries: self
.entries
.iter()
.map(|(spec, emb)| PersistedEntry {
spec: spec.clone(),
embedding: emb.clone(),
})
.collect(),
};
let raw = serde_json::to_vec(&persisted)?;
let tmp = path.with_extension("json.tmp");
tokio::fs::write(&tmp, &raw).await?;
tokio::fs::rename(&tmp, path).await?;
Ok(())
}
/// Build by embedding each control's requirement text.
pub async fn build(llm: &LlmClient, specs: Vec<ControlCheckSpec>) -> Result<Self, CoreError> {
if specs.is_empty() {
return Ok(Self {
entries: Vec::new(),
});
}
let texts: Vec<String> = specs.iter().map(|s| s.requirement.clone()).collect();
let embeddings = llm
.embed(texts)
.await
.map_err(|e| CoreError::Llm(e.to_string()))?;
Ok(Self {
entries: specs.into_iter().zip(embeddings).collect(),
})
}
pub fn len(&self) -> usize {
self.entries.len()
}
pub fn is_empty(&self) -> bool {
self.entries.is_empty()
}
/// The top-`k` control specs whose embedding is nearest (cosine) to `query`.
pub fn nearest(&self, query: &[f64], k: usize) -> Vec<ControlCheckSpec> {
let mut scored: Vec<(f64, &ControlCheckSpec)> = self
.entries
.iter()
.map(|(spec, emb)| (cosine(query, emb), spec))
.collect();
scored.sort_by(|a, b| b.0.total_cmp(&a.0));
scored.into_iter().take(k).map(|(_, s)| s.clone()).collect()
}
}
/// Cosine similarity; 0.0 for length-mismatched, empty, or zero vectors.
fn cosine(a: &[f64], b: &[f64]) -> f64 {
if a.len() != b.len() || a.is_empty() {
return 0.0;
}
let dot: f64 = a.iter().zip(b).map(|(x, y)| x * y).sum();
let na: f64 = a.iter().map(|x| x * x).sum();
let nb: f64 = b.iter().map(|x| x * x).sum();
if na == 0.0 || nb == 0.0 {
return 0.0;
}
dot / (na.sqrt() * nb.sqrt())
}
#[cfg(test)]
mod tests {
use super::*;
use compliance_core::models::finding::Severity;
fn spec(id: &str) -> ControlCheckSpec {
ControlCheckSpec {
control_id: id.into(),
title: id.into(),
requirement: id.into(),
default_cwe: None,
severity: Severity::Medium,
}
}
#[test]
fn nearest_ranks_by_cosine() {
let index = ControlIndex::from_embeddings(vec![
(spec("a"), vec![1.0, 0.0]),
(spec("b"), vec![0.0, 1.0]),
(spec("c"), vec![0.7, 0.7]),
]);
let hits = index.nearest(&[0.9, 0.1], 2);
assert_eq!(hits.len(), 2);
assert_eq!(hits[0].control_id, "a"); // closest to [0.9,0.1]
}
#[test]
fn cosine_edges_are_zero() {
assert_eq!(cosine(&[1.0], &[1.0, 2.0]), 0.0); // length mismatch
assert_eq!(cosine(&[0.0, 0.0], &[1.0, 1.0]), 0.0); // zero vector
assert!((cosine(&[1.0, 0.0], &[1.0, 0.0]) - 1.0).abs() < 1e-9); // identical
}
#[test]
fn corpus_hash_is_stable_and_identity_sensitive() {
let a = corpus_hash(&[spec("x"), spec("y")]);
assert_eq!(a, corpus_hash(&[spec("x"), spec("y")])); // same corpus → same hash
assert_ne!(a, corpus_hash(&[spec("y"), spec("x")])); // reorder → different
assert_ne!(a, corpus_hash(&[spec("x")])); // fewer controls → different
}
#[tokio::test]
#[allow(clippy::unwrap_used)]
async fn cache_round_trips_and_misses_on_corpus_change() {
let dir = std::env::temp_dir().join(format!("cidx-{}", uuid::Uuid::new_v4()));
let path = dir.join("control-index.json");
let specs = [spec("a"), spec("b")];
let hash = corpus_hash(&specs);
let index = ControlIndex::from_embeddings(vec![
(spec("a"), vec![1.0, 0.0]),
(spec("b"), vec![0.0, 1.0]),
]);
index.write_cache(&path, &hash).await.unwrap();
// matching corpus hash → hit
let loaded = ControlIndex::load_cache(&path, &hash).await.unwrap();
assert_eq!(loaded.len(), 2);
assert_eq!(loaded.nearest(&[0.9, 0.1], 1)[0].control_id, "a");
// corpus changed → miss (forces a rebuild)
assert!(ControlIndex::load_cache(&path, "differenthash")
.await
.is_none());
// absent file → miss, not an error
assert!(
ControlIndex::load_cache(dir.join("nope.json").as_path(), &hash)
.await
.is_none()
);
let _ = std::fs::remove_dir_all(&dir);
}
}
+1 -6
View File
@@ -6,18 +6,13 @@
//! and snapshots it locally.
mod checker;
mod index;
mod judge;
mod oscal_provider;
mod scan_triage;
mod semantic;
mod surface;
mod triage;
pub use checker::GroundedControlChecker;
pub use index::ControlIndex;
pub use judge::{ControlJudge, LlmControlJudge, PROMPT_VERSION};
pub use oscal_provider::OscalControlsProvider;
pub use scan_triage::{grounded_surface_findings, semantic_stamp_findings, triage_repo_findings};
pub use semantic::SemanticControlChecker;
pub use scan_triage::triage_repo_findings;
pub use triage::{ControlTriage, TriageOutcome};
+31 -27
View File
@@ -43,20 +43,20 @@ impl OscalControlsProvider {
}
}
fn catalog_url(&self, framework: &str) -> String {
fn catalog_url(&self, framework: ComplianceFramework) -> String {
format!(
"{}/api/compliance/v1/oscal/catalog?framework={framework}",
self.base_url.trim_end_matches('/')
)
}
fn snapshot_path(&self, framework: &str) -> PathBuf {
fn snapshot_path(&self, framework: ComplianceFramework) -> PathBuf {
self.snapshot_dir
.join(format!("oscal-catalog-{framework}.json"))
}
/// Fetch the raw catalog bytes for a framework token over HTTP.
async fn fetch_raw(&self, framework: &str) -> Result<Vec<u8>, CoreError> {
/// Fetch the raw catalog bytes for a framework over HTTP.
async fn fetch_raw(&self, framework: ComplianceFramework) -> Result<Vec<u8>, CoreError> {
let mut req = self.http.get(self.catalog_url(framework));
if let Some(token) = &self.token {
req = req.bearer_auth(token.expose_secret());
@@ -78,7 +78,11 @@ impl OscalControlsProvider {
}
/// Write a catalog snapshot atomically (temp file + rename).
async fn write_snapshot(&self, framework: &str, raw: &[u8]) -> Result<(), CoreError> {
async fn write_snapshot(
&self,
framework: ComplianceFramework,
raw: &[u8],
) -> Result<(), CoreError> {
tokio::fs::create_dir_all(&self.snapshot_dir).await?;
let path = self.snapshot_path(framework);
let tmp = path.with_extension("json.tmp");
@@ -88,7 +92,10 @@ impl OscalControlsProvider {
}
/// Read a previously written snapshot, if one exists.
async fn read_snapshot(&self, framework: &str) -> Result<Option<OscalDocument>, CoreError> {
async fn read_snapshot(
&self,
framework: ComplianceFramework,
) -> Result<Option<OscalDocument>, CoreError> {
match tokio::fs::read(self.snapshot_path(framework)).await {
Ok(raw) => Ok(Some(serde_json::from_slice(&raw)?)),
Err(e) if e.kind() == std::io::ErrorKind::NotFound => Ok(None),
@@ -96,21 +103,21 @@ impl OscalControlsProvider {
}
}
/// Load the catalog for a framework token: fetch fresh + snapshot the exact
/// bytes; on network failure, fall back to the last snapshot so scans run.
async fn load_token(&self, framework: &str) -> Result<OscalDocument, CoreError> {
/// Load the catalog for a framework: fetch fresh + snapshot the exact bytes;
/// on network failure, fall back to the last snapshot so scans still run.
pub async fn load(&self, framework: ComplianceFramework) -> Result<OscalDocument, CoreError> {
match self.fetch_raw(framework).await {
Ok(raw) => {
let doc: OscalDocument = serde_json::from_slice(&raw)?;
if let Err(e) = self.write_snapshot(framework, &raw).await {
tracing::warn!(framework, error = %e, "failed to write OSCAL snapshot");
tracing::warn!(%framework, error = %e, "failed to write OSCAL snapshot");
}
Ok(doc)
}
Err(fetch_err) => match self.read_snapshot(framework).await? {
Some(doc) => {
tracing::warn!(
framework, error = %fetch_err,
%framework, error = %fetch_err,
"OSCAL catalog fetch failed; falling back to snapshot"
);
Ok(doc)
@@ -119,17 +126,6 @@ impl OscalControlsProvider {
},
}
}
/// Load the OSCAL catalog for a compliance framework.
pub async fn load(&self, framework: ComplianceFramework) -> Result<OscalDocument, CoreError> {
self.load_token(&framework.to_string()).await
}
/// Load the code-checkable master-controls catalog
/// (`?framework=master-controls`).
pub async fn load_master_controls(&self) -> Result<OscalDocument, CoreError> {
self.load_token("master-controls").await
}
}
/// Order controls whose title/text mention the query context first (stable), then
@@ -185,11 +181,11 @@ mod tests {
fn builds_catalog_url_and_snapshot_path() {
let p = provider(std::path::Path::new("/snap"));
assert_eq!(
p.catalog_url("cra"),
p.catalog_url(ComplianceFramework::Cra),
"http://unused/api/compliance/v1/oscal/catalog?framework=cra"
);
assert_eq!(
p.snapshot_path("cra"),
p.snapshot_path(ComplianceFramework::Cra),
std::path::Path::new("/snap/oscal-catalog-cra.json")
);
}
@@ -217,11 +213,19 @@ mod tests {
async fn snapshot_round_trip_and_offline_fallback() {
let dir = std::env::temp_dir().join(format!("oscal-test-{}", uuid::Uuid::new_v4()));
let p = provider(&dir);
assert!(p.read_snapshot("cra").await.unwrap().is_none());
p.write_snapshot("cra", MINI_CATALOG.as_bytes())
assert!(p
.read_snapshot(ComplianceFramework::Cra)
.await
.unwrap()
.is_none());
p.write_snapshot(ComplianceFramework::Cra, MINI_CATALOG.as_bytes())
.await
.unwrap();
let doc = p.read_snapshot("cra").await.unwrap().unwrap();
let doc = p
.read_snapshot(ComplianceFramework::Cra)
.await
.unwrap()
.unwrap();
assert_eq!(doc.to_controls().len(), 1);
assert_eq!(doc.framework(), Some(ComplianceFramework::Cra));
let _ = std::fs::remove_dir_all(&dir);
+1 -153
View File
@@ -16,16 +16,9 @@ use compliance_core::models::onboarding::ComplianceFramework;
use compliance_core::AgentConfig;
use control_map::ControlMap;
use super::surface;
use super::{
ControlIndex, ControlTriage, GroundedControlChecker, LlmControlJudge, OscalControlsProvider,
SemanticControlChecker, TriageOutcome,
};
use super::{ControlTriage, LlmControlJudge, OscalControlsProvider, TriageOutcome};
use crate::llm::LlmClient;
/// Nearest master controls judged per code region in the semantic pass.
const SEMANTIC_TOP_K: usize = 5;
/// Lines of context to read on each side of a finding's line.
const REGION_WINDOW: usize = 6;
@@ -106,50 +99,6 @@ async fn build_specs(provider: &OscalControlsProvider) -> HashMap<String, Contro
specs
}
/// Absence-based control pass (the grounded half of the hybrid coverage): for each
/// control with a [`surface`] definition, deterministically retrieve the code
/// surfaces it governs (login routes, logging setup, update/download code) and have
/// the grounded judge decide whether the control holds there. Returns net-new
/// findings, each already tagged with its control and grounded to a real snippet.
///
/// Gated: the orchestrator runs this only when `breakpilot.grounded_control_checks`
/// is set. Absence detection is the least deterministic path (the judge decides
/// presence/absence, not a syntactic pattern), so it stays off until tuned live.
pub async fn grounded_surface_findings(
config: &AgentConfig,
llm: Arc<LlmClient>,
repo_path: &Path,
repo_id: &str,
) -> Vec<Finding> {
let Some(base_url) = config.breakpilot.base_url.clone() else {
return Vec::new();
};
let provider = OscalControlsProvider::new(
reqwest::Client::new(),
base_url,
config.breakpilot.token.clone(),
&config.breakpilot.snapshot_dir,
);
let specs = build_specs(&provider).await;
if specs.is_empty() {
return Vec::new();
}
let checker = GroundedControlChecker::new(LlmControlJudge::new(llm));
let mut out = Vec::new();
for surf in surface::SURFACES {
let Some(spec) = specs.get(surf.control_id) else {
continue; // catalog doesn't carry this control
};
let regions = surface::retrieve(repo_path, surf.terms);
if regions.is_empty() {
continue;
}
out.extend(checker.check(spec, &regions, repo_id).await);
}
out
}
/// Read a window of lines around `line` (1-based) from `repo_path/file`.
fn fetch_region(repo_path: &Path, file: &str, line: u32) -> Option<CandidateRegion> {
let content = std::fs::read_to_string(repo_path.join(file)).ok()?;
@@ -167,107 +116,6 @@ fn fetch_region(repo_path: &Path, file: &str, line: u32) -> Option<CandidateRegi
})
}
/// Master-controls **semantic** pass: for each finding's code region, retrieve the
/// top-K nearest master controls by embedding, have the grounded judge confirm,
/// and stamp the confirmed control ids onto the finding — the scale path for the
/// ~13.6k master-control corpus (which has no CWE to LUT on). Returns the number
/// of findings that gained a master-control ref.
///
/// Gated: the orchestrator runs this only when `breakpilot.semantic_mapping` is
/// set (default off, flipped on once the master-controls catalog is live). The
/// control embedding index is built once and cached to `snapshot_dir` keyed by
/// corpus hash ([`ControlIndex::load_or_build`]), so only the first scan after a
/// catalog change pays the embedding cost.
pub async fn semantic_stamp_findings(
config: &AgentConfig,
llm: Arc<LlmClient>,
repo_path: &Path,
findings: &mut [Finding],
) -> usize {
let Some(base_url) = config.breakpilot.base_url.clone() else {
return 0;
};
let provider = OscalControlsProvider::new(
reqwest::Client::new(),
base_url,
config.breakpilot.token.clone(),
&config.breakpilot.snapshot_dir,
);
let doc = match provider.load_master_controls().await {
Ok(d) => d,
Err(e) => {
tracing::warn!(error = %e, "master-controls catalog unavailable; skipping semantic pass");
return 0;
}
};
let specs: Vec<ControlCheckSpec> = doc
.to_controls()
.into_iter()
.map(|c| ControlCheckSpec {
control_id: c.id,
title: c.title,
requirement: c.text,
default_cwe: None,
severity: Severity::Medium,
})
.collect();
let cache_path =
Path::new(&config.breakpilot.snapshot_dir).join("control-index-master-controls.json");
let index = match ControlIndex::load_or_build(&llm, specs, &cache_path).await {
Ok(i) if !i.is_empty() => i,
Ok(_) => return 0,
Err(e) => {
tracing::warn!(error = %e, "failed to embed master-controls corpus");
return 0;
}
};
let checker = SemanticControlChecker::new(LlmControlJudge::new(llm.clone()));
let mut tagged = 0;
for finding in findings.iter_mut() {
if finding.status == FindingStatus::FalsePositive {
continue;
}
let (Some(file), Some(line)) = (finding.file_path.clone(), finding.line_number) else {
continue;
};
let Some(region) = fetch_region(repo_path, &file, line) else {
continue;
};
let region_emb = match llm.embed(vec![region.content.clone()]).await {
Ok(mut embs) => match embs.pop() {
Some(v) => v,
None => continue,
},
Err(e) => {
tracing::warn!(error = %e, "region embed failed; skipping finding");
continue;
}
};
let confirmed = checker
.check(
&index,
&region,
&region_emb,
SEMANTIC_TOP_K,
&finding.repo_id,
)
.await;
let before = finding.control_refs.len();
for f in confirmed {
for cref in f.control_refs {
if !finding.control_refs.contains(&cref) {
finding.control_refs.push(cref);
}
}
}
if finding.control_refs.len() > before {
tagged += 1;
}
}
tagged
}
#[cfg(test)]
mod tests {
use super::*;
-119
View File
@@ -1,119 +0,0 @@
//! Semantic control mapping: retrieve the top-K controls nearest a code region,
//! then confirm each with the grounded judge.
//!
//! The `region → controls` direction (vs. the CWE-LUT's `finding → control`) is
//! what scales to the full master-control corpus: the LLM only ever judges a
//! handful of retrieved candidates, and every surviving verdict is still anchored
//! to real code by the grounding gate.
use compliance_core::control_check::{ground, CandidateRegion};
use compliance_core::models::Finding;
use super::index::ControlIndex;
use super::judge::ControlJudge;
/// Retrieve → judge → ground, generic over the judge so tests use a stub.
pub struct SemanticControlChecker<J> {
judge: J,
}
impl<J: ControlJudge> SemanticControlChecker<J> {
pub fn new(judge: J) -> Self {
Self { judge }
}
/// Map a code region to the controls it violates. `region_embedding` is the
/// region's embedding (the caller computes it via the LLM); the top-`k`
/// nearest controls in `index` are judged and grounded.
pub async fn check(
&self,
index: &ControlIndex,
region: &CandidateRegion,
region_embedding: &[f64],
k: usize,
repo_id: &str,
) -> Vec<Finding> {
let candidates = index.nearest(region_embedding, k);
let mut findings = Vec::new();
for spec in &candidates {
let verdict = self.judge.judge(spec, region).await;
if let Some(finding) = ground(spec, region, &verdict, repo_id) {
findings.push(finding);
}
}
findings
}
}
#[cfg(test)]
mod tests {
use super::*;
use compliance_core::control_check::{ControlCheckSpec, LlmVerdict};
use compliance_core::models::finding::Severity;
struct StubJudge {
verdict: LlmVerdict,
}
impl ControlJudge for StubJudge {
async fn judge(&self, _s: &ControlCheckSpec, _r: &CandidateRegion) -> LlmVerdict {
self.verdict.clone()
}
}
fn spec(id: &str) -> ControlCheckSpec {
ControlCheckSpec {
control_id: id.into(),
title: id.into(),
requirement: id.into(),
default_cwe: None,
severity: Severity::Medium,
}
}
#[tokio::test]
async fn retrieves_then_grounds_the_nearest_control() {
let index = ControlIndex::from_embeddings(vec![
(spec("mc-near"), vec![1.0, 0.0]),
(spec("mc-far"), vec![0.0, 1.0]),
]);
let checker = SemanticControlChecker::new(StubJudge {
verdict: LlmVerdict {
violates: true,
snippet: "PASSWORD = \"admin\"".into(),
cwe: None,
confidence: 0.9,
},
});
let region = CandidateRegion {
file: "src/auth.py".into(),
start_line: 1,
content: "PASSWORD = \"admin\"\n".into(),
};
// Query embedding nearest to mc-near; k=1 → only mc-near is judged.
let findings = checker
.check(&index, &region, &[0.95, 0.05], 1, "repo")
.await;
assert_eq!(findings.len(), 1);
assert_eq!(findings[0].control_refs, vec!["mc-near".to_string()]);
}
#[tokio::test]
async fn ungrounded_verdict_is_dropped() {
let index = ControlIndex::from_embeddings(vec![(spec("mc-near"), vec![1.0, 0.0])]);
let checker = SemanticControlChecker::new(StubJudge {
verdict: LlmVerdict {
violates: true,
snippet: "not in the region".into(),
cwe: None,
confidence: 0.9,
},
});
let region = CandidateRegion {
file: "f".into(),
start_line: 1,
content: "real code\n".into(),
};
let findings = checker.check(&index, &region, &[1.0, 0.0], 1, "repo").await;
assert!(findings.is_empty());
}
}
-246
View File
@@ -1,246 +0,0 @@
//! Surface retrieval for absence-based controls.
//!
//! Some CRA controls are violated by an *absence* — no rate limiting on login, no
//! security logging, no signature check on an update — so there's no offending
//! pattern for semgrep to match. Instead we deterministically locate the code
//! *surface* the control governs (a login route, a logging setup, update/download
//! code) by identifier/route terms, then hand each surface region to the grounded
//! judge, which decides whether the control is satisfied there. The resulting
//! finding grounds to the surface snippet, so nothing fabricated survives.
//!
//! Retrieval is intentionally cheap and bounded: keyword match + a fixed window,
//! capped per control to keep the downstream LLM cost predictable.
use std::path::Path;
use compliance_core::control_check::CandidateRegion;
/// An absence-based control and the case-insensitive terms that mark the code
/// surface it governs.
pub struct Surface {
pub control_id: &'static str,
pub terms: &'static [&'static str],
}
/// The absence-based CRA controls we retrieve surfaces for — the grounded half of
/// the hybrid coverage (the pattern-expressible half is custom semgrep rules).
pub const SURFACES: &[Surface] = &[
Surface {
control_id: "cra-ai-6", // Integritaetspruefung
terms: &[
"checksum",
"sha256",
"signature",
"hmac",
"integrity",
"verify",
],
},
Surface {
control_id: "cra-ai-11", // Brute-Force-Schutz
terms: &[
"login",
"signin",
"authenticate",
"/auth",
"password",
"ratelimit",
],
},
Surface {
control_id: "cra-ai-24", // Security-Logging
terms: &["login", "authorize", "permission", "role", "admin", "audit"],
},
Surface {
control_id: "cra-ai-27", // Log-Integritaet und -Aufbewahrung
terms: &["logging", "logger", "getlogger", "audit_log"],
},
Surface {
control_id: "cra-ai-28", // Sichere Update-Mechanismen
terms: &["update", "upgrade", "download", "firmware"],
},
Surface {
control_id: "cra-ai-29", // Update-Authentizitaet
terms: &["update", "signature", "verify", "pubkey", "certificate"],
},
Surface {
control_id: "cra-ai-30", // Update-Integritaet
terms: &["update", "checksum", "digest", "integrity", "verify"],
},
];
/// Source file extensions worth reading (skip binaries/assets/lockfiles).
const CODE_EXTS: &[&str] = &[
"py", "js", "ts", "tsx", "jsx", "go", "java", "rb", "php", "rs", "cs", "kt",
];
/// Directories never worth walking.
const SKIP_DIRS: &[&str] = &[
".git",
"node_modules",
"target",
"vendor",
".venv",
"__pycache__",
"dist",
"build",
];
/// Lines of context on each side of a hit.
const WINDOW: usize = 6;
/// Cap on regions per control, to bound downstream LLM calls.
const MAX_REGIONS_PER_CONTROL: usize = 8;
/// Skip files larger than this (generated/minified).
const MAX_FILE_BYTES: u64 = 512 * 1024;
/// Deterministically retrieve up to [`MAX_REGIONS_PER_CONTROL`] code regions in
/// `repo_path` whose lines mention any of `terms`. Hits close together within a
/// file are merged into one region; results are capped to bound LLM cost.
pub fn retrieve(repo_path: &Path, terms: &[&str]) -> Vec<CandidateRegion> {
let lowered: Vec<String> = terms.iter().map(|t| t.to_lowercase()).collect();
let mut regions = Vec::new();
for entry in walk(repo_path) {
if regions.len() >= MAX_REGIONS_PER_CONTROL {
break;
}
let path = entry.path();
if !has_code_ext(path) {
continue;
}
let Ok(meta) = entry.metadata() else { continue };
if !meta.is_file() || meta.len() > MAX_FILE_BYTES {
continue;
}
let Ok(content) = std::fs::read_to_string(path) else {
continue;
};
let rel = path
.strip_prefix(repo_path)
.unwrap_or(path)
.to_string_lossy()
.to_string();
let lines: Vec<&str> = content.lines().collect();
let hits: Vec<usize> = lines
.iter()
.enumerate()
.filter(|(_, line)| {
let ll = line.to_lowercase();
lowered.iter().any(|t| ll.contains(t.as_str()))
})
.map(|(i, _)| i)
.collect();
for center in merge_centers(&hits) {
if regions.len() >= MAX_REGIONS_PER_CONTROL {
break;
}
let start = center.saturating_sub(WINDOW);
let end = (center + WINDOW + 1).min(lines.len());
regions.push(CandidateRegion {
file: rel.clone(),
start_line: (start as u32) + 1,
content: lines[start..end].join("\n"),
});
}
}
regions
}
/// Collapse ascending hit indices that fall within one window into a single
/// representative center, so overlapping regions aren't judged repeatedly.
fn merge_centers(hits: &[usize]) -> Vec<usize> {
let mut out: Vec<usize> = Vec::new();
for &h in hits {
match out.last() {
Some(&last) if h.saturating_sub(last) <= WINDOW => {}
_ => out.push(h),
}
}
out
}
fn has_code_ext(path: &Path) -> bool {
path.extension()
.and_then(|e| e.to_str())
.is_some_and(|e| CODE_EXTS.contains(&e))
}
fn walk(root: &Path) -> Vec<walkdir::DirEntry> {
walkdir::WalkDir::new(root)
.into_iter()
.filter_entry(|e| {
let name = e.file_name().to_string_lossy();
!SKIP_DIRS.contains(&name.as_ref())
})
.filter_map(|e| e.ok())
.collect()
}
#[cfg(test)]
#[allow(clippy::unwrap_used)]
mod tests {
use super::*;
fn write(dir: &Path, rel: &str, body: &str) {
let p = dir.join(rel);
if let Some(parent) = p.parent() {
std::fs::create_dir_all(parent).unwrap();
}
std::fs::write(p, body).unwrap();
}
fn terms_for(control_id: &str) -> &'static [&'static str] {
SURFACES
.iter()
.find(|s| s.control_id == control_id)
.unwrap()
.terms
}
#[test]
fn surfaces_cover_the_absence_based_controls() {
assert_eq!(SURFACES.len(), 7);
for id in [
"cra-ai-6",
"cra-ai-11",
"cra-ai-24",
"cra-ai-27",
"cra-ai-28",
"cra-ai-29",
"cra-ai-30",
] {
assert!(SURFACES.iter().any(|s| s.control_id == id), "{id} missing");
}
}
#[test]
fn retrieves_matching_region_with_context() {
let dir = std::env::temp_dir().join(format!("surface-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&dir).unwrap();
write(
&dir,
"app/auth.py",
"import x\n\n\n\n\n\n\ndef login(u, p):\n return check(u, p)\n",
);
let regions = retrieve(&dir, terms_for("cra-ai-11"));
assert_eq!(regions.len(), 1);
assert!(regions[0].content.contains("def login"));
assert_eq!(regions[0].file, "app/auth.py");
let _ = std::fs::remove_dir_all(&dir);
}
#[test]
fn skips_non_code_and_vendored() {
let dir = std::env::temp_dir().join(format!("surface-{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&dir).unwrap();
write(&dir, "README.md", "login and password and audit\n"); // not code ext
write(&dir, "node_modules/pkg/index.js", "function login() {}\n"); // vendored
assert!(retrieve(&dir, terms_for("cra-ai-11")).is_empty());
let _ = std::fs::remove_dir_all(&dir);
}
#[test]
fn merges_adjacent_hits_into_one_region() {
// Two hits one line apart collapse to a single center/region.
assert_eq!(merge_centers(&[10, 11, 30]), vec![10, 30]);
assert_eq!(merge_centers(&[]), Vec::<usize>::new());
assert_eq!(merge_centers(&[5]), vec![5]);
}
}
+4 -54
View File
@@ -44,14 +44,10 @@ impl<J: ControlJudge> ControlTriage<J> {
/// Triage one tool finding. `region` is the code around the finding, used as
/// the grounding evidence for the judge.
pub async fn triage(&self, finding: &Finding, region: &CandidateRegion) -> TriageOutcome {
// Match by CWE (off-the-shelf findings) and/or rule id (our custom
// detectors, which carry no LUT-bound CWE). A finding with neither is
// simply unmapped.
let mapped = self.map.controls_for_finding(
&finding.scanner,
finding.cwe.as_deref(),
finding.rule_id.as_deref(),
);
let Some(cwe) = finding.cwe.as_deref() else {
return TriageOutcome::Unmapped;
};
let mapped = self.map.controls_for(&finding.scanner, cwe);
if mapped.is_empty() {
return TriageOutcome::Unmapped;
}
@@ -166,52 +162,6 @@ mod tests {
assert_eq!(out, TriageOutcome::FalsePositive);
}
#[tokio::test]
async fn custom_rule_finding_without_cwe_is_confirmed() {
// A custom detector finding carries a rule id but no LUT-bound CWE; it must
// still map (by rule id) and confirm.
let mut specs = specs();
specs.insert(
"cra-ai-1".to_string(),
ControlCheckSpec {
control_id: "cra-ai-1".into(),
title: "Secure-by-Default".into(),
requirement: "Ship secure defaults".into(),
default_cwe: None,
severity: Severity::Medium,
},
);
let triage = ControlTriage::new(
StubJudge {
verdict: LlmVerdict {
violates: true,
snippet: "app.run(debug=True)".into(),
cwe: None,
confidence: 0.9,
},
},
ControlMap::cra().unwrap(),
specs,
);
let mut f = Finding::new(
"repo".into(),
"fp".into(),
"semgrep".into(),
ScanType::Sast,
"flask debug".into(),
"desc".into(),
Severity::Medium,
);
f.rule_id = Some("tmp.x.cra-ai-1-flask-debug-enabled".into()); // no cwe
let region = CandidateRegion {
file: "app.py".into(),
start_line: 1,
content: "app.run(debug=True)\n".into(),
};
let out = triage.triage(&f, &region).await;
assert_eq!(out, TriageOutcome::Confirmed(vec!["cra-ai-1".to_string()]));
}
#[tokio::test]
async fn unmapped_cwe_is_left_untagged() {
let triage = ControlTriage::new(
@@ -230,53 +230,6 @@ impl PipelineOrchestrator {
tracing::info!("[{repo_id}] Control triage tagged {tagged} findings with control refs");
}
// Stage 5c: semantic control mapping — scale path for the master-controls
// corpus (no CWE to LUT on): embed each finding's region, retrieve the
// nearest master controls, grounded-judge, and stamp confirmed refs. Gated
// (default off) as the corpus embedding + per-finding judging is the heavy
// path; enabled once verified live against a deployed master-controls catalog.
if self.config.breakpilot.semantic_mapping {
self.update_phase(scan_run_id, "semantic_control_mapping")
.await;
let sem = crate::controls::semantic_stamp_findings(
&self.config,
self.llm.clone(),
&repo_path,
&mut all_findings,
)
.await;
if sem > 0 {
tracing::info!(
"[{repo_id}] Semantic mapping tagged {sem} findings with master-control refs"
);
}
}
// Stage 5d: grounded surface checks — the absence-based controls (no
// rate limiting, no security logging, no update-signature check) have no
// syntactic pattern to match, so we retrieve the code surface each governs
// and let the grounded judge decide whether it holds, producing net-new
// findings already tagged + grounded. Gated (default off): absence
// detection is the least deterministic path, kept off until tuned live.
if self.config.breakpilot.grounded_control_checks {
self.update_phase(scan_run_id, "grounded_control_checks")
.await;
let grounded = crate::controls::grounded_surface_findings(
&self.config,
self.llm.clone(),
&repo_path,
&repo_id,
)
.await;
if !grounded.is_empty() {
tracing::info!(
"[{repo_id}] Grounded surface checks raised {} control findings",
grounded.len()
);
all_findings.extend(grounded);
}
}
// Dedup against existing findings and insert new ones
let mut new_count = 0u32;
let mut new_findings: Vec<Finding> = Vec::new();
+25 -45
View File
@@ -1,4 +1,4 @@
use std::path::{Path, PathBuf};
use std::path::Path;
use compliance_core::models::{Finding, ScanType, Severity};
use compliance_core::traits::{ScanOutput, Scanner};
@@ -6,30 +6,6 @@ use compliance_core::CoreError;
use crate::pipeline::dedup;
/// Custom CRA-control detectors bundled into the binary and staged to a temp file
/// at scan time so semgrep can `--config` them alongside the auto ruleset. These
/// cover controls no off-the-shelf rule digs out (secure defaults, weak password
/// hashing, insecure session cookies, weak data-at-rest ciphers); each rule id is
/// keyed back to its control by the `control-map` LUT.
const CRA_RULES: &str = include_str!("../../rules/cra_semgrep.yaml");
/// Write the bundled CRA rules to a stable temp path (atomic: unique tmp +
/// rename). Returns `None` on failure — the scan then runs with auto rules only.
async fn stage_cra_rules() -> Option<PathBuf> {
let dir = std::env::temp_dir();
let path = dir.join("compliance-cra-semgrep.yaml");
let tmp = dir.join(format!("compliance-cra-semgrep.{}.tmp", std::process::id()));
if let Err(e) = tokio::fs::write(&tmp, CRA_RULES).await {
tracing::warn!(error = %e, "failed to stage custom CRA semgrep rules; using auto rules only");
return None;
}
if let Err(e) = tokio::fs::rename(&tmp, &path).await {
tracing::warn!(error = %e, "failed to stage custom CRA semgrep rules; using auto rules only");
return None;
}
Some(path)
}
pub struct SemgrepScanner;
impl Scanner for SemgrepScanner {
@@ -43,26 +19,30 @@ impl Scanner for SemgrepScanner {
#[tracing::instrument(skip_all)]
async fn scan(&self, repo_path: &Path, repo_id: &str) -> Result<ScanOutput, CoreError> {
let cra_rules = stage_cra_rules().await;
let mut command = tokio::process::Command::new("semgrep");
command.arg("--config=auto");
if let Some(path) = &cra_rules {
command.arg(format!("--config={}", path.display()));
}
command
.args(["--json", "--quiet", "--max-memory", "500", "--jobs", "1"])
.arg(repo_path);
let output = tokio::time::timeout(std::time::Duration::from_secs(600), command.output())
.await
.map_err(|_| CoreError::Scanner {
scanner: "semgrep".to_string(),
source: "timed out after 10 minutes".into(),
})?
.map_err(|e| CoreError::Scanner {
scanner: "semgrep".to_string(),
source: Box::new(e),
})?;
let output = tokio::time::timeout(
std::time::Duration::from_secs(600),
tokio::process::Command::new("semgrep")
.args([
"--config=auto",
"--json",
"--quiet",
"--max-memory",
"500",
"--jobs",
"1",
])
.arg(repo_path)
.output(),
)
.await
.map_err(|_| CoreError::Scanner {
scanner: "semgrep".to_string(),
source: "timed out after 10 minutes".into(),
})?
.map_err(|e| CoreError::Scanner {
scanner: "semgrep".to_string(),
source: Box::new(e),
})?;
if !output.status.success() && output.stdout.is_empty() {
let stderr = String::from_utf8_lossy(&output.stderr);
-12
View File
@@ -75,16 +75,6 @@ pub struct BreakpilotConfig {
pub token: Option<SecretString>,
/// Directory for catalog snapshots.
pub snapshot_dir: String,
/// Enable the master-controls **semantic** mapping pass (embed regions,
/// retrieve nearest controls, grounded-judge). Off by default: it is the
/// scale path and stays gated until verified live against a deployed
/// master-controls catalog.
pub semantic_mapping: bool,
/// Enable the **grounded surface** pass for absence-based controls (retrieve
/// the code surface a control governs, judge whether it holds). Off by
/// default: absence detection is the least deterministic path and stays gated
/// until tuned against live scans.
pub grounded_control_checks: bool,
}
impl Default for BreakpilotConfig {
@@ -93,8 +83,6 @@ impl Default for BreakpilotConfig {
base_url: None,
token: None,
snapshot_dir: "/data/compliance-scanner/oscal".to_string(),
semantic_mapping: false,
grounded_control_checks: false,
}
}
}
+1 -2
View File
@@ -14,14 +14,13 @@
//! The LLM supplies cross-language / cross-stack pattern recognition; this module
//! supplies the determinism.
use serde::{Deserialize, Serialize};
use sha2::{Digest, Sha256};
use crate::models::finding::{Finding, Severity};
use crate::models::scan::ScanType;
/// A control rendered as a check the LLM judges code against.
#[derive(Debug, Clone, Serialize, Deserialize)]
#[derive(Debug, Clone)]
pub struct ControlCheckSpec {
/// Stable control id, e.g. `"cra-ai-8"`.
pub control_id: String,
+19 -60
View File
@@ -5,21 +5,9 @@
{
"control": "cra-ai-1",
"title": "Secure-by-Default-Konfiguration",
"scans": [
{
"tool": "semgrep",
"scan_type": "sast",
"cwe": [],
"rules": [
"cra-ai-1-flask-debug-enabled",
"cra-ai-1-django-debug-true",
"cra-ai-1-tls-verify-disabled",
"cra-ai-1-cors-wildcard"
]
}
],
"note": null,
"status": "covered"
"scans": [],
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
"status": "needs_tooling"
},
{
"control": "cra-ai-2",
@@ -53,24 +41,15 @@
"control": "cra-ai-6",
"title": "Integritaetspruefung",
"scans": [],
"note": "absence-based — no syntactic pattern; covered by the grounded surface check (retrieve surface + LLM judge), gated (BREAKPILOT_GROUNDED_CHECKS) pending live tuning",
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
"status": "needs_tooling"
},
{
"control": "cra-ai-7",
"title": "Starke Authentifizierung",
"scans": [
{
"tool": "semgrep",
"scan_type": "sast",
"cwe": [],
"rules": [
"cra-ai-7-weak-password-hash"
]
}
],
"note": null,
"status": "covered"
"scans": [],
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
"status": "needs_tooling"
},
{
"control": "cra-ai-8",
@@ -121,25 +100,15 @@
{
"control": "cra-ai-10",
"title": "Sitzungsmanagement",
"scans": [
{
"tool": "semgrep",
"scan_type": "sast",
"cwe": [],
"rules": [
"cra-ai-10-session-cookie-insecure",
"cra-ai-10-express-cookie-insecure"
]
}
],
"note": null,
"status": "covered"
"scans": [],
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
"status": "needs_tooling"
},
{
"control": "cra-ai-11",
"title": "Brute-Force-Schutz",
"scans": [],
"note": "absence-based — no syntactic pattern; covered by the grounded surface check (retrieve surface + LLM judge), gated (BREAKPILOT_GROUNDED_CHECKS) pending live tuning",
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
"status": "needs_tooling"
},
{
@@ -169,19 +138,9 @@
{
"control": "cra-ai-14",
"title": "Speicher-Schutz (Data at Rest)",
"scans": [
{
"tool": "semgrep",
"scan_type": "sast",
"cwe": [],
"rules": [
"cra-ai-14-python-weak-cipher",
"cra-ai-14-node-weak-cipher"
]
}
],
"note": null,
"status": "covered"
"scans": [],
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
"status": "needs_tooling"
},
{
"control": "cra-ai-15",
@@ -308,7 +267,7 @@
"control": "cra-ai-24",
"title": "Security-Logging",
"scans": [],
"note": "absence-based — no syntactic pattern; covered by the grounded surface check (retrieve surface + LLM judge), gated (BREAKPILOT_GROUNDED_CHECKS) pending live tuning",
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
"status": "needs_tooling"
},
{
@@ -329,28 +288,28 @@
"control": "cra-ai-27",
"title": "Log-Integritaet und -Aufbewahrung",
"scans": [],
"note": "absence-based — no syntactic pattern; covered by the grounded surface check (retrieve surface + LLM judge), gated (BREAKPILOT_GROUNDED_CHECKS) pending live tuning",
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
"status": "needs_tooling"
},
{
"control": "cra-ai-28",
"title": "Sichere Update-Mechanismen",
"scans": [],
"note": "absence-based — no syntactic pattern; covered by the grounded surface check (retrieve surface + LLM judge), gated (BREAKPILOT_GROUNDED_CHECKS) pending live tuning",
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
"status": "needs_tooling"
},
{
"control": "cra-ai-29",
"title": "Update-Authentizitaet",
"scans": [],
"note": "absence-based — no syntactic pattern; covered by the grounded surface check (retrieve surface + LLM judge), gated (BREAKPILOT_GROUNDED_CHECKS) pending live tuning",
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
"status": "needs_tooling"
},
{
"control": "cra-ai-30",
"title": "Update-Integritaet",
"scans": [],
"note": "absence-based — no syntactic pattern; covered by the grounded surface check (retrieve surface + LLM judge), gated (BREAKPILOT_GROUNDED_CHECKS) pending live tuning",
"note": "code-checkable but no off-the-shelf tool digs it out — author a detector (custom semgrep rule / check)",
"status": "needs_tooling"
},
{
+3 -69
View File
@@ -66,14 +66,6 @@ pub struct ControlMap {
const CRA_MAP_JSON: &str = include_str!("../data/cra_control_map.json");
/// Whether an authored rule id `bound` matches a scanner's emitted rule id
/// `actual`. semgrep prefixes local-rule check_ids with a path
/// (`tmp.compliance-cra-semgrep.cra-ai-1-flask-debug-enabled`), so match the final
/// id segment rather than requiring exact equality.
fn rule_id_matches(bound: &str, actual: &str) -> bool {
actual == bound || actual.ends_with(&format!(".{bound}"))
}
impl ControlMap {
/// Load the built-in CRA control map (the embedded, authored LUT).
pub fn cra() -> Result<Self, MapError> {
@@ -88,28 +80,12 @@ impl ControlMap {
/// Controls whose bindings include the given `tool` + `cwe` — used to attach a
/// raw tool finding back to the control(s) it's evidence for.
pub fn controls_for(&self, tool: &str, cwe: &str) -> Vec<&ControlEntry> {
self.controls_for_finding(tool, Some(cwe), None)
}
/// Controls a tool finding is evidence for, matched by CWE and/or the specific
/// rule id that fired. Off-the-shelf findings bind by CWE; our custom detectors
/// bind by rule id (precise — a broad CWE would over-attribute and then the
/// grounded judge could drop a genuine finding as a control false positive).
pub fn controls_for_finding(
&self,
tool: &str,
cwe: Option<&str>,
rule_id: Option<&str>,
) -> Vec<&ControlEntry> {
self.controls
.iter()
.filter(|c| {
c.scans.iter().any(|s| {
s.tool == tool
&& (cwe.is_some_and(|w| s.cwe.iter().any(|x| x == w))
|| rule_id
.is_some_and(|r| s.rules.iter().any(|b| rule_id_matches(b, r))))
})
c.scans
.iter()
.any(|s| s.tool == tool && s.cwe.iter().any(|w| w == cwe))
})
.collect()
}
@@ -184,46 +160,4 @@ mod tests {
assert!(s.needs_tooling > 0);
assert!(s.not_code_checkable > 0);
}
#[test]
fn rule_id_matching_handles_semgrep_path_prefix() {
let bound = "cra-ai-1-flask-debug-enabled";
assert!(rule_id_matches(bound, bound)); // exact
assert!(rule_id_matches(
bound,
"tmp.compliance-cra-semgrep.cra-ai-1-flask-debug-enabled"
)); // semgrep path prefix
assert!(!rule_id_matches(
bound,
"cra-ai-1-flask-debug-enabled-extra"
)); // not a suffix segment
assert!(!rule_id_matches(
bound,
"python.lang.security.exec-detected"
)); // unrelated
}
#[test]
fn custom_rule_finding_attaches_to_control_by_rule_id() {
let map = ControlMap::cra().unwrap();
// cra-ai-1 is now tool-covered by custom rules.
assert_eq!(map.coverage("cra-ai-1").unwrap().status, Coverage::Covered);
// A prefixed check_id still maps back to cra-ai-1 by rule id.
let hits =
map.controls_for_finding("semgrep", None, Some("tmp.x.cra-ai-1-tls-verify-disabled"));
assert!(hits.iter().any(|c| c.control == "cra-ai-1"));
}
#[test]
fn custom_rule_controls_do_not_bind_by_broad_cwe() {
let map = ControlMap::cra().unwrap();
// cra-ai-1 rules emit CWE-489 in metadata, but the LUT binds by rule id
// only (cwe: []) — so a stray CWE-489 finding must NOT attach to it.
assert!(map.controls_for("semgrep", "CWE-489").is_empty());
// The CWE path for off-the-shelf findings is unchanged.
assert!(map
.controls_for("semgrep", "CWE-798")
.iter()
.any(|c| c.control == "cra-ai-8"));
}
}